Merge remote-tracking branch 'nccl/master' into 2.8.3

[ROCm/rccl commit: c985358e11]
Этот коммит содержится в:
Wenkai Du
2021-02-15 19:29:45 +00:00
родитель ea2e665834 fc7bdb38a5
Коммит ab71643c99
23 изменённых файлов: 82 добавлений и 52 удалений
+1 -1
Просмотреть файл
@@ -25,7 +25,7 @@ extern pthread_mutex_t ncclDebugOutputLock;
extern FILE *ncclDebugFile;
extern ncclResult_t getHostName(char* hostname, int maxlen, const char delim);
void ncclDebugLog(ncclDebugLogLevel level, unsigned long flags, const char *filefunc, int line, const char *fmt, ...);
void ncclDebugLog(ncclDebugLogLevel level, unsigned long flags, const char *filefunc, int line, const char *fmt, ...) __attribute__ ((format (printf, 5, 6)));
// Let code temporarily downgrade WARN into INFO
extern thread_local int ncclDebugNoWarn;
+2
Просмотреть файл
@@ -40,10 +40,12 @@ ncclResult_t ncclTopoSetAffinity(struct ncclTopoSystem* system, int rank);
#define NCCL_TOPO_CPU_ARCH_ARM 3
#define NCCL_TOPO_CPU_VENDOR_INTEL 1
#define NCCL_TOPO_CPU_VENDOR_AMD 2
#define NCCL_TOPO_CPU_VENDOR_ZHAOXIN 3
#define NCCL_TOPO_CPU_TYPE_BDW 1
#define NCCL_TOPO_CPU_TYPE_SKL 2
#define NCCL_TOPO_CPU_TYPE_ZEN 3
#define NCCL_TOPO_CPU_TYPE_ROME 4
#define NCCL_TOPO_CPU_TYPE_YONGFENG 1
ncclResult_t ncclTopoCpuType(struct ncclTopoSystem* system, int* arch, int* vendor, int* model);
ncclResult_t ncclTopoGetNetCount(struct ncclTopoSystem* system, int* count);
+1 -1
Просмотреть файл
@@ -46,7 +46,7 @@ static ncclResult_t shmOpen(const char* shmname, const int shmsize, void** shmPt
*shmPtr = ptr;
return ncclSuccess;
sysError:
WARN("Error while %s shared memory segment %s (size %d)\n", create ? "creating" : "attaching to", shmname, shmsize);
WARN("Error while %s shared memory segment %s (size %d)", create ? "creating" : "attaching to", shmname, shmsize);
hipError:
if (fd != -1) close(fd);
if (create) shm_unlink(shmname);
+1 -1
Просмотреть файл
@@ -372,7 +372,7 @@ static ncclResult_t connectAddress(int* fd, union socketAddress* remoteAddr) {
/* IPv4/IPv6 support */
int family = remoteAddr->sa.sa_family;
if (family != AF_INET && family != AF_INET6) {
WARN("Error : connecting to address with family %d is neither AF_INET(%d) nor AF_INET6(%d)\n", family, AF_INET, AF_INET6);
WARN("Error : connecting to address with family %d is neither AF_INET(%d) nor AF_INET6(%d)", family, AF_INET, AF_INET6);
return ncclInternalError;
}
int salen = (family == AF_INET) ? sizeof(sockaddr_in) : sizeof(sockaddr_in6);